Advertisement

Reliability-Aware and Robust Multi-sensor Fusion Toward Ego-Lane Estimation Using Artificial Neural Networks

  • Tran Tuan NguyenEmail author
  • Jan-Ole Perschewski
  • Fabian Engel
  • Jonas Kruesemann
  • Jonas Sitzmann
  • Jens Spehr
  • Sebastian Zug
  • Rudolf Kruse
Chapter
Part of the Information Fusion and Data Science book series (IFDS)

Abstract

In the field of road estimation, incorporating multiple sensors is essential to achieve a robust performance. However, the reliability of each sensor changes due to environmental conditions. Thus, we propose a reliability-aware fusion concept, which takes into account the sensor reliabilities. By that, the reliabilities are estimated explicitly or implicitly by classification algorithms, which are trained with extracted information from the sensors and their past performance compared to ground truth data. During the fusion, these estimated reliabilities are then exploited to avoid the impact of unreliable sensors. In order to prove our concept, we apply our fusion approach to a redundant sensor setup for intelligent vehicles containing three-camera systems, several lidars, and radar sensors. Since artificial neural networks (ANN) have produced great results for many applications, we explore two ways of incorporating them into our fusion concept. On the one hand, we use ANN as classifiers to explicitly estimate the sensors’ reliabilities. On the other hand, we utilize ANN to directly predict the ego-lane from sensor information, where the reliabilities are implicitly learned. By the evaluation with real-world recording data, the direct ANN approach leads to satisfactory road estimation.

Keywords

Information fusion Reliability Neural networks Ego-lane estimation Intelligent vehicles 

References

  1. 1.
    D. Töpfer, J. Spehr, J. Effertz, C. Stiller, Efficient scene understanding for intelligent vehicles using a part-based road representation, in IEEE Conference on Intelligent Transportation Systems (2013), pp. 65–70. https://doi.org/10.1109/ITSC.2013.6728212
  2. 2.
    T.T. Nguyen, J. Spehr, M. Uhlemann, S. Zug, R. Kruse, Learning of lane information reliability for intelligent vehicles, in IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (2016), pp. 142–147. https://doi.org/10.1109/MFI.2016.7849480
  3. 3.
    T.T. Nguyen, J. Spehr, J. Xiong, M. Baum, S. Zug, R. Kruse, Online reliability assessment and reliability-aware fusion for ego-lane detection using influence diagram and Bayes filter, in IEEE Conference on Multisensor Fusion and Integration for Intelligent Systems (2017), pp. 7–14Google Scholar
  4. 4.
    T.T. Nguyen, J. Spehr, S. Zug, R. Kruse, Multi-source fusion for robust road detection using online estimated reliabilities. IEEE Trans. Indus. Inf. 1 (2018). https://doi.org/10.1109/TII.2018.2865582
  5. 5.
    C. Chen, A. Seff, A. Kornhauser, J. Xiao, DeepDriving: learning affordance for direct perception in autonomous driving, in IEEE International Conference on Computer Vision (2015), pp. 2722–2730Google Scholar
  6. 6.
    D.A. Pomerleau, Efficient training of artificial neural networks for autonomous navigation. Neural Comput. 3(1), 88–97 (1991). https://doi.org/10.1162/neco.1991.3.1.88 CrossRefGoogle Scholar
  7. 7.
    M. Bojarski, D.D. Testa, D. Dworakowski, B. Firner, B. Flepp, P. Goyal, L.D. Jackel, M. Monfort, U. Muller, J. Zhang, X. Zhang, J. Zhao, K. Zieba, End to end learning for self-driving cars (2016). CoRR abs/1604.07316Google Scholar
  8. 8.
    Z. Chen, X. Huang, End-to-end learning for lane keeping of self-driving cars, in 2017 IEEE Intelligent Vehicles Symposium (IV) (2017), pp. 1856–1860. https://doi.org/10.1109/IVS.2017.7995975
  9. 9.
    F. Codevilla, M. Müller, A. Dosovitskiy, A. López, V. Koltun, End-to-end driving via conditional imitation learning (2017). CoRR abs/1710.02410Google Scholar
  10. 10.
    A. Oliva, A. Torralba, Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput. Vis. 42(3), 145–175 (2001). https://doi.org/10.1023/A:1011139631724 CrossRefGoogle Scholar
  11. 11.
    M. Al-Qizwini, I. Barjasteh, H. Al-Qassab, H. Radha, Deep learning algorithm for autonomous driving using googlenet, in 2017 IEEE Intelligent Vehicles Symposium (IV) (2017), pp. 89–96. https://doi.org/10.1109/IVS.2017.7995703
  12. 12.
    C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going deeper with convolutions (2014). ArXiv e-printsGoogle Scholar
  13. 13.
    K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition (2014). CoRR abs/1409.1556Google Scholar
  14. 14.
    M.D. Zeiler, R. Fergus, Visualizing and understanding convolutional networks (2013). CoRR abs/1311.2901Google Scholar
  15. 15.
    O. Hartmann, M. Gabb, R. Schweiger, K. Dietmayer, Towards autonomous self-assessment of digital maps, in Proceedings of the IEEE Intelligent Vehicles Symposium (2014), pp. 89–95. https://doi.org/10.1109/IVS.2014.6856564
  16. 16.
    G.L. Rogova, V. Nimier, Reliability in information fusion: literature survey, in 7th International Conference On Information Fusion (2004), pp. 1158–1165Google Scholar
  17. 17.
    T. Brade, S. Zug, J. Kaiser, Validity-based failure algebra for distributed sensor systems, in IEEE International Symposium on Reliable Distributed Systems (2013), pp. 143–152. https://doi.org/10.1109/SRDS.2013.23
  18. 18.
    H. Frigui, L. Zhang, P. Gader, Context-dependent multi-sensor fusion for landmine detection, in Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (2008), pp. II–371–II–374. https://doi.org/10.1109/IGARSS.2008.4779005
  19. 19.
    T.T. Nguyen, J. Spehr, J.-O. Perschewski, F. Engel, S. Zug, R. Kruse, Zuverlässigkeitsbasierte Fusion von Fahrstreifeninformationen für Fahrerassistenzfunktionen, in Proceedings 27. Workshop Computational Intelligence, ed. by F. Hoffmann, E. Hüllermeier, R. Mikut (KIT Scientific Publishing, Karlsruhe, 2017), pp. 33–49Google Scholar
  20. 20.
    T.T. Nguyen, J. Spehr, J. Sitzmann, M. Baum, S. Zug, R. Kruse: Improving ego-lane detection by incorporating source reliability, in Multisensor Fusion and Integration in the Wake of Big Data, Deep Learning and Cyber Physical System, ed. by S. Lee, H. Ko, S. Oh. Lecture Notes in Electrical Engineering, vol. 501 (Springer International Publishing, Cham, 2018)Google Scholar
  21. 21.
    M. Realpe, B.X. Vintimilla, L. Vlacic, A fault tolerant perception system for autonomous vehicles, in Proceedings of the 35th Chinese Control Conference (2016), pp. 6531–6536. https://doi.org/10.1109/ChiCC.2016.7554385
  22. 22.
    A. Rechy Romero, P.V. Koerich Borges, A. Elfes, A. Pfrunder, Environment-aware sensor fusion for obstacle detection, in Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (2016), pp. 114–121. https://doi.org/10.1109/MFI.2016.7849476
  23. 23.
    T.T. Nguyen, J. Spehr, D. Vock, M. Baum, S. Zug, R. Kruse, A general reliability-aware fusion concept using DST and supervised learning with its applications in multi-source road estimation, in 2018 IEEE Intelligent Vehicles Symposium (IV) (2018), pp. 597–604Google Scholar
  24. 24.
    F.E. White, A model for data fusion, in Proceedings of the First National Symposium on Sensor Fusion (1988)Google Scholar
  25. 25.
    C. Gackstatter, P. Heinemann, S. Thomas, B. Rosenhahn, G. Klinker: Fusion of clothoid segments for a more accurate and updated prediction of the road geometry, in 13th International IEEE Intelligent Transportation Systems Conference (2010), pp. 1691–1696. https://doi.org/10.1109/ITSC.2010.5625270
  26. 26.
    T.T. Nguyen, J. Spehr, H. Lin, D. Lipinski, Fused raised pavement marker detection using 2D-Lidar and mono camera, in IEEE International Conference on Intelligent Transportation Systems (2015), pp. 2346–2351Google Scholar
  27. 27.
    E.D. Dickmanns, B.D. Mysliwetz, Recursive 3-D road and relative ego-state recognition. IEEE Trans. Pattern Anal. Mach. Intell. 14(2), 199–213 (1992). https://doi.org/10.1109/34.121789 CrossRefGoogle Scholar
  28. 28.
    T.T. Nguyen, J. Spehr, J. Xiong, M. Baum, S. Zug, R. Kruse, A survey of performance measures to evaluate ego-lane estimation and a novel sensor-independent measure along with its applications, in IEEE Conference on Multisensor Fusion and Integration for Intelligent Systems (2017), pp. 239–246Google Scholar
  29. 29.
    A. Kraskov, H. Stögbauer, P. Grassberger, Estimating mutual information. Phys. Rev. E Stat. Nonlinear Soft Matt. Phys. 69(6 Pt 2), 066138 (2004). https://doi.org/10.1103/PhysRevE.69.066138
  30. 30.
    J. Pradeep, E. Srinivasan, S. Himavathi, Diagonal based feature extraction for handwritten character recognition system using neural network, in 2011 3rd International Conference on Electronics Computer Technology (ICECT) (2011), pp. 364–368. https://doi.org/10.1109/ICECTECH.2011.5941921
  31. 31.
    A. Graves, A.R. Mohamed, G. Hinton, Speech recognition with deep recurrent neural networks, in 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2013), pp. 6645–6649. https://doi.org/10.1109/ICASSP.2013.6638947
  32. 32.
    R. Kruse, C. Borgelt, C. Braune, S. Mostaghim, M. Steinbrecher, Computational Intelligence: A Methodological Introduction. Texts in Computer Science, 2nd edn./2016 edn. (Springer, London, 2016)Google Scholar
  33. 33.
    C.M. Bishop, Pattern Recognition and Machine Learning. Information Science and Statistics (Springer, New York, 2006)zbMATHGoogle Scholar
  34. 34.
    L. Bottou, Stochastic gradient descent tricks, in Neural Networks: Tricks of the Trade, ed. by G. Montavon, G.B. Orr, K.R. Müller, 2nd edn. (Springer, Berlin/Heidelberg, 2012), pp. 421–436CrossRefGoogle Scholar
  35. 35.
    L. Bottou, Stochastic gradient learning in neural networks. Proc. Neuro-Nımes 91(8), 687–696 (1991)Google Scholar
  36. 36.
    N. Qian, On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145–151 (1999). https://doi.org/10.1016/S0893-6080(98)00116-6, http://www.sciencedirect.com/science/article/pii/S0893608098001166
  37. 37.
    I. Sutskever, J. Martens, G. Dahl, G. Hinton, On the importance of initialization and momentum in deep learning, in Proceedings of the 30th International Conference on Machine Learning – Volume 28, ICML’13 (2013), pp. III–1139–III–1147. http://dl.acm.org/citation.cfm?id=3042817.3043064
  38. 38.
    G. Shafer, A Mathematical Theory of Evidence (Princeton University Press, Princeton, 1976)zbMATHGoogle Scholar
  39. 39.
    M. Aeberhard, S. Paul, N. Kaempchen, T. Bertram, Object existence probability fusion using dempster-shafer theory in a high-level sensor data fusion architecture, in Proceedings of IEEE Intelligent Vehicles Symposium (2011), pp. 770–775. https://doi.org/10.1109/IVS.2011.5940430
  40. 40.
    A.E. Albert, A.L. Albert, Regression and the Moore-Penrose Pseudoinverse. Mathematics in Science and Engineering: A Series of Monographs and Textbooks (Academic, New York, 1972)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Tran Tuan Nguyen
    • 1
    Email author
  • Jan-Ole Perschewski
    • 1
  • Fabian Engel
    • 1
  • Jonas Kruesemann
    • 1
  • Jonas Sitzmann
    • 1
  • Jens Spehr
    • 1
  • Sebastian Zug
    • 2
  • Rudolf Kruse
    • 2
  1. 1.Volkswagen AktiengesellschaftWolfsburgGermany
  2. 2.Faculty of Computer ScienceOtto-von-Guericke University MagdeburgMagdeburgGermany

Personalised recommendations